GenAI Daily for Practitioners

Executive Summary • Here are the concise, non-sensationalist bullets for enterprise practitioners: • Safety and accuracy in large language models follow different scaling laws, with safety improving faster than accuracy as model size increases. (Item 1) • Transformers with selective access to early representations improve performance and efficiency in certain tasks. (Item 2) • InvisibleInk generates high-utility text with differential privacy at a lower cost than baseline methods. (Item 3) • Workspace-Bench 1.0 provides a benchmark for evaluating AI agents on tasks with large-scale file dependencies. (Item 4) • Rethinking retrieval in agentic search systems: Evaluating and advancing retrievers to improve performance. (Item 5) • Hybrid models for natural language reasoning outperform single-model approaches in syllogistic logic tasks. (Item 6)

Research

• Safety and accuracy follow different scaling laws in clinical large language models \ Clinical LLMs are often scaled by increasing model size, context length, retrieval complexity, or inference-time compute, with the implicit expectation that higher accuracy implies safer behavior. This assumption is incomplete in medicine,… \ Source • arXiv cs.CL • 19:57
• Transformers with Selective Access to Early Representations \ Several recent Transformer architectures expose later layers to representations computed in the earliest layers, motivated by the observation that low-level features can become harder to recover as the residual stream is repeatedly transfo… \ Source • arXiv cs.CL • 18:38
• InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy \ As major progress in LLM-based long-form text generation enables paradigms such as retrieval-augmented generation (RAG) and inference-time scaling, safely incorporating private information into the generation remains a critical open questi… \ Source • arXiv cs.CL • 12:38
• Workspace-Bench 1.0: Benchmarking AI Agents on Workspace Tasks with Large-Scale File Dependencies \ Workspace learning requires AI agents to identify, reason over, exploit, and update explicit and implicit dependencies among heterogeneous files in a worker's workspace, enabling them to complete both routine and advanced tasks effectively… \ Source • arXiv cs.CL • 12:17
• Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems \ Reasoning-intensive retrieval aims to surface evidence that supports downstream reasoning rather than merely matching topical similarity. This capability is increasingly important for agentic search systems, where retrievers must provide c… \ Source • arXiv cs.CL • 19:42
• Hybrid Models for Natural Language Reasoning: The Case of Syllogistic Logic \ Despite the remarkable progress in neural models, their ability to generalize, a cornerstone for applications such as logical reasoning, remains a critical challenge. We delineate two fundamental aspects of this ability: compositionality, … \ Source • arXiv cs.CL • 17:51
• TriBench-Ko: Evaluating LLM Risks in Judicial Workflows \ Large language models (LLMs) are increasingly integrated into legal workflows. However, existing benchmarks primarily address proxy tasks, such as bar examination performance or classification, which fail to capture the performance and ris… \ Source • arXiv cs.CL • 16:20
• A Comprehensive Evaluation of Deep Learning Object Detection Models on Heterogeneous Edge Devices \ Modern applications such as autonomous vehicles, intelligent surveillance, and smart city systems increasingly require object detection on resource-constrained edge devices. Yet, there is still limited understanding of how different object… \ Source • arXiv cs.LG • 13:26
• Reproducing Complex Set-Compositional Information Retrieval \ Complex information needs may involve set-compositional queries using conjunction, disjunction, and exclusion, yet it remains unclear whether current retrieval paradigms genuinely satisfy such constraints or exploit `semantic shortcuts'. W… \ Source • arXiv cs.CL • 16:51
• Natural Language Processing: A Comprehensive Practical Guide from Tokenisation to RLHF \ This preprint presents a systematic, research-oriented practicum that guides the reader through the entire modern NLP pipeline: from tokenisation and vectorisation to fine-tuning of large language models, retrieval-augmented generation, an… \ Source • arXiv cs.CL • 16:25
• PatRe: A Full-Stage Office Action and Rebuttal Generation Benchmark for Patent Examination \ Patent examination is a complex, multi-stage process requiring both technical expertise and legal reasoning, increasingly challenged by rising application volumes. Prior benchmarks predominantly view patent examination as discriminative cl… \ Source • arXiv cs.CL • 11:42
• CuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification \ Discharge summaries require extracting critical information from lengthy electronic health records (EHRs), a process that is labor-intensive when performed manually. Large language models (LLMs) can improve generation efficiency; however, … \ Source • arXiv cs.CL • 10:05

Big Tech

No items today.

Regulation & Standards

No items today.

Enterprise Practice

No items today.

Open-Source Tooling

No items today.

— Personal views, not IBM. No tracking. Curated automatically; links under 24h old.